Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating legal obligations or liabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ekl
    -0.16
    ccount
    -0.15
    ë¡ľëĤĺ
    -0.14
    (éĩij
    -0.14
    .dm
    -0.14
    moth
    -0.14
    plevel
    -0.14
    ilk
    -0.14
    fid
    -0.13
    dex
    -0.13
    POSITIVE LOGITS
    enza
    0.17
    enas
    0.15
    ourt
    0.15
     purpose
    0.15
     Hatch
    0.14
     www
    0.14
     sake
    0.14
    anger
    0.14
    forge
    0.14
    è¡¥
    0.14
    Act Density 0.010%

    No Known Activations